Methodological Synergy in Practice: PLS‑SEM–ANN Fusion For Modelling E‑Learning Adoption Dynamics in Ghanaian Technical Universities

Purpose: This study examines the key determinants shaping the adoption of cloud computing–based e‑learning in Ghana’s technical universities, offering a deeper insight into lecturers’ behavioural intentions through a dual analytical framework that integrates both explanatory and predictive modelling approaches. Design/Methodology/Approach: A hybrid framework integrating Structural Equation Modelling (SEM) and Artificial Neural Networks (ANN) was employed. Data were collected from 1,258 faculty members via a structured questionnaire. SEM validated linear relationships among constructs, while ANN captured non‑linear dynamics and enhanced predictive accuracy. Research Limitation: The study is limited by its cross‑sectional design and focus on Ghanaian technical universities, which restricts generalisability. Future research should adopt longitudinal approaches and include diverse institutional contexts to enrich insights. Findings: Comparative analysis revealed both convergence and divergence between SEM and ANN. E‑Infrastructure Readiness consistently emerged as the most influential predictor, underscoring the importance of robust digital infrastructure. Cloud Computing Complexity also showed significant positive influence, while Anxiety unexpectedly exerted a positive effect, suggesting lecturers’ motivation to adopt new technologies to avoid obsolescence. Divergences in rankings highlighted ANN’s ability to uncover latent dynamics overlooked by linear modelling. Practical Implication: The findings highlight the need for investment in infrastructure, training, and technical support to strengthen adoption and ensure effective integration of cloud‑based e‑learning. Social Implication: Increased adoption of cloud-based e‑learning can expand access to digital education, foster inclusivity, and contribute to national capacity building in higher education. Originality/Value: This study offers a robust methodological contribution that captures both statistically significant linear and complex non‑linear influences, enriching understanding of adoption dynamics and guiding institutional and policy strategies.